Predictors of Users’ Willingness to Personalize Web Search

Younus, Arjumand; O’Riordan, Colm; Pasi, Gabriella

doi:10.1007/978-3-642-40769-7_40

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intuitively, mentions account for highly specific conversations and represent specific user interests. Note that this is in contrast to our previous findings where mentions were found to be negatively correlated with a preference for personalization [8,10]; and this further proves the need for a more reliable means of observing user search behavior instead of reliance on user survey results. Finally, Table 3 depicts a significant outcome of a user's Twitter content being highly reflective of his/her information-seeking needs, and personalization entropy is low (meaning high preference for personalized urls).…”

Section: Resultscontrasting

confidence: 94%

“…-Tweeting Behavior: This aspect captures the amount of user engagement over Twitter in the form of number of tweets, mentions and retweets. We also include tweeting frequency as a mechanism to measure Twitter usage frequency [8,10]. -Twitter Network: This aspect captures statistics about a user's Twitter network such as number of followers, number of Twitterers followed, number of Twitterers retweeted, number of Twitterers mentioned etc.…”

Section: Experimental Methodologymentioning

confidence: 99%

“…We conducted a similar study previously [8,10] whereby a user survey was conducted to gather data about users' personalization preferences and their social network usage habits. However, the reliance on user survey responses limits the usefulness of those studies and in this work we attempt to make useful and reliable inferences through utilization of online evaluation methods.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Analysis of Privacy-Aware Personalization Signals by Using Online Evaluation Methods

Younus,

Qureshi

2017

Preprint

Self Cite

View full text Add to dashboard Cite

Personalization despite being an effective solution to the problem information overload remains tricky on account of multiple dimensions to consider. Furthermore, the challenge of avoiding overdoing personalization involves estimation of a user's preferences in relation to different queries. This work is an attempt to make inferences about when personalization would be beneficial by relating observable user behavior to his/her social network usage patterns and user-generated content. User behavior on a search system is observed by means of team-draft interleaving whereby results from two retrieval functions are presented in an interleaved manner, and user clicks are utilised to infer preference for a certain retrieval function. This improves upon earlier work which had limited usefulness due to reliance on user survey results; our findings may aid real-time personalization in search systems by detecting a user-related and query-related personalization signals.

show abstract

Section: Resultscontrasting

confidence: 94%

Section: Experimental Methodologymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation